{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33462173", "kind": "science-record", "revision": 9, "content_hash": "sha256:0f612fb2af91a05540a526ab4549ba4e36607d33676717ad83369b10e537d892", "created_at": "2026-11-01T15:41:23Z", "updated_at": "2026-11-01T22:46:00Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Bioinformatics Analysis of Differentially Expressed Genes and Protein-Protein Interaction Networks Associated with Functional Pathways in Ulcerative Colitis.", "doi": "10.12659/MSM.927917", "pmid": "33462173", "authors": ["Feng Cao", "Yun-Sheng Cheng", "Liang Yu", "Yan-Yan Xu", "Yong Wang"], "journal": "Medical science monitor : international medical journal of experimental and clinical research", "year": 2021, "abstract": "BACKGROUND This bioinformatics study aimed to identify differentially expressed genes (DEGs) and protein-protein interaction (PPI) networks associated with functional pathways in ulcerative colitis based on 3 Gene Expression Omnibus (GEO) datasets. MATERIAL AND METHODS The GSE87466, GSE75214, and GSE48958 MINiML formatted family files were downloaded from the GEO database. DEGs were identified from the 3 datasets, and volcano maps and heat maps were drawn after R language standardization and analysis, respectively. Venn diagram software was used to identify common DEGs. PPI analysis of common DEGs was performed using the Search Tool for the Retrieval of Interacting Genes. Gene modules and hub genes were visualized in the PPI network using Cytoscape. Enrichment analysis was performed for all common DEGs, module genes, and hub genes. RESULTS A total of 90 DEGs were selected, which included 3 functional modules and 1 hub gene module. CXCL8 module genes were mainly enriched in cytokine-mediated signaling pathways and interleukin (IL)-10 signaling. CCL20 module genes were mainly enriched in the IL-17 signaling pathway and cellular response to IL-1. Hub gene modules mainly involved IL-10, IL-4, and IL-13 signaling pathways. CXCL8, CXCL1, and IL-1ß were the top 3 hub genes and were mainly involved in IL-10 signaling. CONCLUSIONS Bioinformatics analysis using 3 GEO datasets identified CXCL8, CXCL1, and IL-1ß, which are involved in IL-10 signaling, as the top 3 hub genes in ulcerative colitis. The findings from this study remain to be validated, but they may contribute to the further understanding of the pathogenesis of ulcerative colitis.", "claims": [{"id": "claim-method", "statement": "We used |logFC| >1.5 and P<0.05 as standards to identify DEGs through the “limma” R software package.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33462173", "locator": "sections[4] \"Data processing and screening of DEGs\" paragraph 2", "quote": "We used |logFC| >1.5 and P<0.05 as standards to identify DEGs through the “limma” R software package."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The GSE87466, GSE75214, and GSE48958 datasets contained 21, 11, and 8 normal tissue samples and 87, 97, and 13 UC colon tissue samples, respectively.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33462173", "locator": "sections[3] \"Dataset information\" paragraph 2", "quote": "The GSE87466, GSE75214, and GSE48958 datasets contained 21, 11, and 8 normal tissue samples and 87, 97, and 13 UC colon tissue samples, respectively."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:33462173"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "complete", "blocked_on": null, "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE48958"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {"log2fc_threshold": "oftware package, using |logFC| > 1"}, "inputs": ["data:geo:GSE48958"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33462173", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.12659/MSM.927917", "sha256": "sha256:bcbf11cb8adcbe80ad85cde9694a35fde522a9809ed7ed2f7eb3bb8766adb1b3", "bytes": 30407, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.12659/MSM.927917", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7824989", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE48958", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE48958", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE48958", "version": null, "note": "The GSE87466, GSE75214, and GSE48958 datasets contained 21, 11, and 8 normal tissue samples and 87, 97, and 13 UC colon tissue samples, respectively.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GSE87466, GSE75214, and GSE48958 datasets contained 21, 11, and 8 normal tissue samples and 87, 97, and 13 UC colon tissue samples, respectively.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1187602", "GSM1187603", "GSM1187604", "GSM1187605", "GSM1187606", "GSM1187607", "GSM1187608", "GSM1187609", "GSM1187610", "GSM1187611", "GSM1187612", "GSM1187613", "GSM1187614", "GSM1187615", "GSM1187616", "GSM1187617", "GSM1187618", "GSM1187619", "GSM1187620", "GSM1187621", "GSM1187622"], "sample_count": 21, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Mucosal gene expression profiling in (un)inflamed colon of patients with ulcerative colitis (UC)", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE75214", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE75214", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE75214", "version": null, "note": "The GSE87466, GSE75214, and GSE48958 datasets contained 21, 11, and 8 normal tissue samples and 87, 97, and 13 UC colon tissue samples, respectively.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GSE87466, GSE75214, and GSE48958 datasets contained 21, 11, and 8 normal tissue samples and 87, 97, and 13 UC colon tissue samples, respectively.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1426071", "GSM1426072", "GSM1426073", "GSM1426074", "GSM1426075", "GSM1426076", "GSM1426077", "GSM1426078", "GSM1426079", "GSM1426080", "GSM1426081", "GSM1426082", "GSM1426083", "GSM1426084", "GSM1426085", "GSM1426086", "GSM1426087", "GSM1426088", "GSM1426089", "GSM1426090", "GSM1426091", "GSM1426092", "GSM1426093", "GSM1426094", "GSM1426095", "GSM1426096", "GSM1426097", "GSM1426098", "GSM1426099", "GSM1426100", "GSM1426101", "GSM1426102", "GSM1426103", "GSM1426104", "GSM1426105", "GSM1426106", "GSM1426107", "GSM1426108", "GSM1426109", "GSM1426110", "GSM1426111", "GSM1426112", "GSM1426113", "GSM1426114", "GSM1426115", "GSM1426116", "GSM1426117", "GSM1426118", "GSM1426119", "GSM1426120", "GSM1426121", "GSM1426122", "GSM1426123", "GSM1426124", "GSM1426125", "GSM1426126", "GSM1426127", "GSM1426128", "GSM1426129", "GSM1426130", "GSM1426131", "GSM1426132", "GSM1426133", "GSM1426134", "GSM1426135", "GSM1426136", "GSM1426137", "GSM1426138", "GSM1426139", "GSM1426140", "GSM1426141", "GSM1426142", "GSM1426143", "GSM1426144", "GSM1426145", "GSM1426146", "GSM1426147", "GSM1426148", "GSM1426149", "GSM1426150", "GSM1426151", "GSM1426152", "GSM1426153", "GSM1426154", "GSM1426155", "GSM1426156", "GSM1426157", "GSM1426158", "GSM1426159", "GSM1426160", "GSM1426161", "GSM1426162", "GSM1426163", "GSM1426164", "GSM1426165", "GSM1426166", "GSM1426167", "GSM1426168", "GSM1426169", "GSM1426170", "GSM1426171", "GSM1426172", "GSM1426173", "GSM1426174", "GSM1426175", "GSM1426176", "GSM1426177", "GSM1426178", "GSM1426179", "GSM1426180", "GSM1426181", "GSM1426182", "GSM1426183", "GSM1426184", "GSM1426185", "GSM1426186", "GSM1945759", "GSM1945760", "GSM1945761", "GSM1945762", "GSM1945763", "GSM1945764", "GSM1945765", "GSM1945766", "GSM1945767", "GSM1945768", "GSM1945769", "GSM1945770", "GSM1945771", "GSM1945772", "GSM1945773", "GSM1945774", "GSM1945775", "GSM1945776", "GSM1945777", "GSM1945778", "GSM1945779", "GSM1945780", "GSM1945781", "GSM1945782", "GSM1945783", "GSM1945784", "GSM1945785", "GSM1945786", "GSM1945787", "GSM1945788", "GSM1945789", "GSM1945790", "GSM1945791", "GSM1945792", "GSM1945793", "GSM1945794", "GSM1945795", "GSM1945796", "GSM1945797", "GSM1945798", "GSM1945799", "GSM1945800", "GSM1945801", "GSM1945802", "GSM1945803", "GSM1945804", "GSM1945805", "GSM1945806", "GSM1945807", "GSM1945808", "GSM1945809", "GSM1945810", "GSM1945811", "GSM1945812", "GSM1945813", "GSM1945814", "GSM1945815", "GSM1945816", "GSM1945817", "GSM1945818", "GSM1945819", "GSM1945820", "GSM1945821", "GSM1945822", "GSM1945823", "GSM1945824", "GSM1945825", "GSM1945826", "GSM1945827", "GSM1945828", "GSM1945829", "GSM1945830", "GSM1945831", "GSM1945832", "GSM1945833", "GSM1945834", "GSM1945835", "GSM1945836"], "sample_count": 194, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Mucosal gene expression profiling in patients with inflammatory bowel disease study", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE87466", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE87466", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE87466", "version": null, "note": "The GSE87466, GSE75214, and GSE48958 datasets contained 21, 11, and 8 normal tissue samples and 87, 97, and 13 UC colon tissue samples, respectively.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GSE87466, GSE75214, and GSE48958 datasets contained 21, 11, and 8 normal tissue samples and 87, 97, and 13 UC colon tissue samples, respectively.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM2332098", "GSM2332099", "GSM2332100", "GSM2332101", "GSM2332102", "GSM2332103", "GSM2332104", "GSM2332105", "GSM2332106", "GSM2332107", "GSM2332108", "GSM2332109", "GSM2332110", "GSM2332111", "GSM2332112", "GSM2332113", "GSM2332114", "GSM2332115", "GSM2332116", "GSM2332117", "GSM2332118", "GSM2332119", "GSM2332120", "GSM2332121", "GSM2332122", "GSM2332123", "GSM2332124", "GSM2332125", "GSM2332126", "GSM2332127", "GSM2332128", "GSM2332129", "GSM2332130", "GSM2332131", "GSM2332132", "GSM2332133", "GSM2332134", "GSM2332135", "GSM2332136", "GSM2332137", "GSM2332138", "GSM2332139", "GSM2332140", "GSM2332141", "GSM2332142", "GSM2332143", "GSM2332144", "GSM2332145", "GSM2332146", "GSM2332147", "GSM2332148", "GSM2332149", "GSM2332150", "GSM2332151", "GSM2332152", "GSM2332153", "GSM2332154", "GSM2332155", "GSM2332156", "GSM2332157", "GSM2332158", "GSM2332159", "GSM2332160", "GSM2332161", "GSM2332162", "GSM2332163", "GSM2332164", "GSM2332165", "GSM2332166", "GSM2332167", "GSM2332168", "GSM2332169", "GSM2332170", "GSM2332171", "GSM2332172", "GSM2332173", "GSM2332174", "GSM2332175", "GSM2332176", "GSM2332177", "GSM2332178", "GSM2332179", "GSM2332180", "GSM2332181", "GSM2332182", "GSM2332183", "GSM2332184", "GSM2332185", "GSM2332186", "GSM2332187", "GSM2332188", "GSM2332189", "GSM2332190", "GSM2332191", "GSM2332192", "GSM2332193", "GSM2332194", "GSM2332195", "GSM2332196", "GSM2332197", "GSM2332198", "GSM2332199", "GSM2332200", "GSM2332201", "GSM2332202", "GSM2332203", "GSM2332204", "GSM2332205"], "sample_count": 108, "group_sizes": null, "group_sizes_basis": null, "platform": "13158", "taxon": "Homo sapiens", "title": "Gene expression profiling of mucosal biopsies from adult patients with moderately to severely active ulcerative colitis", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:33462173:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:8ca8bfc441f85a6c4d2b73eb685512f17f17aa6a1c08a37337b43a6f7ed5612f", "bytes": 2391, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#t1-medscimonit-27-e927917", "version": null, "note": "The Gene Ontology enrichment analysis of the top 3 hub genes.", "structure": {"pmcid": "PMC7824989", "section_index": 12, "section_title": "Further enrichment analysis of the module genes and hub genes", "row_count": 4, "column_count": 4}, "table": {"label": "Table 1", "caption": "The Gene Ontology enrichment analysis of the top 3 hub genes.", "rows": [["Genes", "Biological process", "Cellular component", "Molecular function"], ["CXCL8", "GO: 0001525 angiogenesis;GO: 0002237 response to molecule of bacterial origin;GO: 0006935 chemotaxis;GO: 0006952 defense response;GO: 0006954 inflammatory response;GO: 0006955 immune response;GO: 0007050 cell cycle arrest;GO: 0007165 signal transduction;GO: 0007186 G protein-coupled receptor signaling pathway;GO: 0008285 negative regulation of cell proliferation", "GO: i0005576 extracellular region;GO: 0005615 extracellular space", "GO: 0005125 cytokine activity;GO: 0005153 interleukin-8 receptor binding;GO: 0005515 protein binding;GO: 0008009 chemokine activity"], ["CXCL1", "GO: 0006935 chemotaxis;GO: 0006952 defense response;GO: 0006954 inflammatory response;GO: 0006955 immune response;GO: 0007165 signal transduction;GO: 0007186 G protein-coupled receptor signaling pathway;GO: 0007399 nervous system development;GO: 0008285 negative regulation of cell proliferation;GO: 0019221 cytokine-mediated signaling pathway;GO: 0030036 actin cytoskeleton organization;", "GO: 0005576 extracellular region;GO: 0005615 extracellular space;GO: 0035580 specific granule lumen;GO: 1904724 tertiary granule lumen", "GO: 0005102 signaling receptor binding;GO: 0005125 cytokine activity;GO: 0008009 chemokine activity;GO: 0008047 enzyme activator activity;GO: 0008083 growth factor activity"], ["IL1B", "GO: 0000165 MAPK cascade;GO: 0000187 activation of MAPK activity;GO: 0001660 fever generation;GO: 0001934 positive regulation of protein phosphorylation;GO: 0002711 positive regulation of T cell mediated immunity;GO: 0006915 apoptotic process;GO: 0006954 inflammatory response;GO: 0006955 immune response;GO: 0007165 signal transduction;GO: 0007267 cell-cell signaling", "GO: 0005576 extracellular region;GO: 0005615 extracellular space;GO: 0005737 cytoplasm;GO: 0005764 lysosome;GO: 0005776 autophagosome; GO: 0005829 cytosol;GO: 0030141 secretory granule;GO: 0031410 cytoplasmic vesicle;GO: 0031982 vesicle", "GO: 0005125 cytokine activity;GO: 0005149 interleukin-1 receptor binding;GO: 0005178 integrin binding;GO: 0005515 protein binding;GO: 0019904 protein domain specific binding"]], "row_count": 4, "column_count": 4, "numeric_cells": 9, "header_rows": 1, "locator": "section[12]/table-wrap[1]#t1-medscimonit-27-e927917"}}, {"id": "asset:table:pmid:33462173:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:dbeb00268119ea2d1011ca94a44693235ab8c359acdfce48c1c8d8852a6c0e3f", "bytes": 1295, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[2]#t2-medscimonit-27-e927917", "version": null, "note": "The main signaling pathway enrichment analysis of the top 3 hub genes.", "structure": {"pmcid": "PMC7824989", "section_index": 12, "section_title": "Further enrichment analysis of the module genes and hub genes", "row_count": 9, "column_count": 5}, "table": {"label": "Table 2", "caption": "The main signaling pathway enrichment analysis of the top 3 hub genes.", "rows": [["Pathway identifier", "Pathway name", "P value", "FDR", "Genes"], ["R-HSA-6783783", "Interleukin-10 signaling", "1.11E-16", "3.11E-15", "CXCL8; CCL20; IL1B; CXCL1; TIMP1; PTGS2"], ["R-HSA-6785807", "Interleukin-4 and Interleukin-13 signaling", "1.11E-16", "3.11E-15", "SOCS3; CXCL8; NOS2; MMP1; IL1B; MMP3; LCN2; TIMP1; PTGS2"], ["R-HSA-449147", "Signaling by Interleukins", "1.11E-16", "3.11E-15", "SOCS3; CXCL8; NOS2; MMP1; CCL20; IL1B; MMP3; LCN2; CXCL1; TIMP1; PTGS2"], ["R-HSA-1280215", "Cytokine signaling in immune system", "1.11E-16", "3.11E-15", "SOCS3; CXCL8; NOS2; MMP1; CCL20; IL1B; MMP3; LCN2; CXCL1; TIMP1; PTGS2"], ["R-HSA-168256", "Immune system", "9.20E-13", "2.02E-11", "CXCL8; NOS2; MMP1; CCL20; MMP3; CXCL1; PTGS2; C3; SOCS3; IL1B; LCN2; CHI3L1; TIMP1"], ["R-HSA-380108", "Chemokine receptors bind chemokines", "6.46E-09", "1.03E-07", "CXCL11; CXCL8; CCL20; CXCL1; CXCL13"], ["R-HSA-375276", "Peptide ligand-binding receptors", "7.91E-07", "9.72E-06", "C3; CXCL11; CXCL8; CCL20; CXCL1; CXCL13"], ["R-HSA-5660668", "CLEC7A/inflammasome pathway", "1.18E-06", "1.30E-05", "IL1B"]], "row_count": 9, "column_count": 5, "numeric_cells": 32, "header_rows": 1, "locator": "section[12]/table-wrap[2]#t2-medscimonit-27-e927917"}}], "gaps": ["asset:data:geo:GSE48958 not downloaded", "asset:data:geo:GSE48958 licence not read", "asset:data:geo:GSE75214 not downloaded", "asset:data:geo:GSE75214 licence not read", "asset:data:geo:GSE87466 not downloaded", "asset:data:geo:GSE87466 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {"log2fc_threshold": "oftware package, using |logFC| > 1"}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We used |logFC| >1.5 and P<0.05 as standards to identify DEGs through the “limma” R software package."}}, {"id": "method-2", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "Protein-Protein Interaction"}}, {"id": "method-3", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "pathway enrichment"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE87466", "GSE75214", "GSE48958"], "resolved_accessions": ["GSE87466", "GSE75214", "GSE48958"], "statements": ["The GSE87466, GSE75214, and GSE48958 datasets contained 21, 11, and 8 normal tissue samples and 87, 97, and 13 UC colon tissue samples, respectively."], "basis": "The paper names GSE87466, GSE75214, GSE48958 in Gene Expression Omnibus (GEO) database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:33462173", "data:geo:GSE48958", "asset:table:pmid:33462173:1", "asset:table:pmid:33462173:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE48958"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:26:24Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 24621, "completion_tokens": 1434, "cached_tokens": 8200}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:33462173", "type": "paper", "label": "pmid:33462173"}, {"id": "source:pmid:33462173", "type": "manuscript", "label": "PMID 33462173 full text"}, {"id": "data:geo:GSE48958", "type": "dataset", "label": "GEO GSE48958"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33462173", "type": "paper", "label": "pmid:33462173"}, {"id": "source:pmid:33462173", "type": "manuscript", "label": "PMID 33462173 full text"}, {"id": "data:geo:GSE48958", "type": "dataset", "label": "GEO GSE48958"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33462173", "type": "extraction", "used": ["source:pmid:33462173"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE48958", "type": "accession_resolution", "used": ["data:geo:GSE48958"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:33462173", "parent_hash": "sha256:c0839ba81558d400f7e5afbf5abc38576f0f97b678154b8b635d1529b95002e7", "fork_of": null, "generation": 8}, "gaps": ["asset:data:geo:GSE48958 licence not read", "asset:data:geo:GSE48958 not downloaded", "asset:data:geo:GSE75214 licence not read", "asset:data:geo:GSE75214 not downloaded", "asset:data:geo:GSE87466 licence not read", "asset:data:geo:GSE87466 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["We used |logFC| >1.5 and P<0.05 as standards to identify DEGs through the “limma” R software package."], "order_basis": "analysis_only", "id": "assay:1"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T03:35:08+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}